CN112802035B - Method for obtaining large-batch samples based on rock mass digital images - Google Patents
Method for obtaining large-batch samples based on rock mass digital images Download PDFInfo
- Publication number
- CN112802035B CN112802035B CN202110260737.7A CN202110260737A CN112802035B CN 112802035 B CN112802035 B CN 112802035B CN 202110260737 A CN202110260737 A CN 202110260737A CN 112802035 B CN112802035 B CN 112802035B
- Authority
- CN
- China
- Prior art keywords
- image
- cutting
- cutting template
- moving
- original image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 12
- 239000011435 rock Substances 0.000 title claims abstract description 9
- 238000005520 cutting process Methods 0.000 claims abstract description 68
- 239000013077 target material Substances 0.000 claims abstract description 9
- 230000009466 transformation Effects 0.000 claims abstract description 5
- 238000011160 research Methods 0.000 abstract description 11
- 239000002689 soil Substances 0.000 abstract description 8
- 239000000463 material Substances 0.000 abstract description 7
- 238000010801 machine learning Methods 0.000 abstract description 4
- 230000001427 coherent effect Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 229910000278 bentonite Inorganic materials 0.000 description 1
- 239000000440 bentonite Substances 0.000 description 1
- SVPXDRXYRYOSEX-UHFFFAOYSA-N bentoquatam Chemical compound O.O=[Si]=O.O=[Al]O[Al]=O SVPXDRXYRYOSEX-UHFFFAOYSA-N 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/60—Rotation of a whole image or part thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
Abstract
The invention discloses a method for acquiring a large number of samples based on a rock mass digital image, and relates to the technical field of image processing. The method comprises the following steps: firstly, obtaining a digital image of a target material to be amplified; then, on the basis of the existing image, carrying out point symmetry and axisymmetry transformation on four vertexes and four sides of the existing image respectively to obtain a new image with the length and width being 3 times that of the original image and the image information being consistent; then, a cutting template is established, the middle point of the cutting template is moved to one of the middle points of the original image in the new image, and the cutting template is cut to obtain the image; and finally, setting a moving step length, moving the cutting template layer by layer, and cutting a plurality of images until the middle point of the cutting template moves to the diagonal point of the starting point in the original image. The invention can complete the whole flow work by computer programming, efficiently and conveniently provide a sufficient number of digital image samples for the machine learning of the rock-soil mass material and other related researches, various parameters of the obtained image samples can be manually adjusted, and the internal image information is coherent.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method for acquiring a large number of samples based on rock mass digital images.
Background
Rock-soil mass materials are widely used in actual production, and related scientific researches are gradually becoming research hotspots. Among them, digital images of related materials are important subjects of research. Such as rock-soil body microscopic images acquired by computer tomography and scanning electron microscope, can acquire various information of pore distribution, and can further acquire permeability, conductivity and other mechanical property indexes of the target material. Further, such as a microscopic image of the concrete material, can provide powerful technical information for its curing use. Meanwhile, the rock-soil body macroscopic image acquired by the camera also has important research value, for example, the development status and trend of cracks of the rock-soil body macroscopic image can be acquired by the surface image of a building, and the rock-soil body macroscopic image can be helpful for maintenance.
In recent years, the rising machine learning provides new directions and ideas for the research of rock-soil mass materials, overcomes the defects of the traditional research method, and better integrates the existing data to provide powerful help for the related research. For example, summarizing and sorting the digital images of the target materials, constructing a data set, selecting a proper model, and training to complete meaningful research work; acquiring a large number of images of the development status of the surface cracks of the building and reasonably training by selecting a machine learning model, so that the lengths, widths, numbers, areas and the like of the cracks of the target materials can be automatically and efficiently identified, a large amount of manpower can be saved, and the accuracy can be improved; a large number of microscopic images of the concrete material are obtained, the images with enough target objects calibrated are arranged, and the distribution situation of various particles in the target material can be automatically identified and calculated by selecting a deep learning model. However, due to the limited number of samples of the target material, high quality digital images with reasonable scaling are difficult to obtain in large quantities, and the existing work is often difficult to develop smoothly due to the limited number of data sets.
Existing approaches to solve such problems mostly employ simple geometric transformations to expand the number of image samples, such as horizontal/vertical flipping, image simple geometric mapping, etc. However, most of the existing methods can only expand the original image sample set by 3-5 times, and in many cases, it is still difficult to expand the number of data sets to meet the needs of research. Therefore, there is still a need to solve the problem that the number of digital image data sets is insufficient.
Disclosure of Invention
According to the invention, the method for acquiring the mass samples based on the rock mass digital image comprises the following steps:
step one: and obtaining a rectangular digital image of the target material to be amplified.
Step two: on the basis of the existing image, point symmetry and axisymmetry transformation are respectively carried out on four vertexes and four sides of the existing image, and a new image which is 3 times longer and wider than the original image and has consistent image information is obtained.
Step three: and (3) establishing a cutting template, moving the middle point of the cutting template to one of the middle points of the original image in the new image, and cutting to obtain the image.
Step four: and selecting a pixel distance with a certain size as a step length according to the size of the original image, moving a cutting template on the new image along one side of the original image, and cutting to obtain one image every time the cutting template moves until the middle point of the cutting template moves to the position of the other vertex on the side.
Step five: the moving direction is turned by 90 degrees, and the new image is moved by a step length along the edge perpendicular to the initial edge in the original image, and an image is obtained by cutting.
Step six: the direction of movement is again turned 90 deg., the cutting template is moved on the new image in the opposite direction of the original edge in the original image, and each time one is moved, an image is obtained by cutting until the midpoint of the cutting template is moved to the opposite other edge perpendicular to the original edge.
Step seven: the moving direction is turned to 90 degrees again, the moving direction is consistent with the direction in the fifth step, one step length is moved, after an image is obtained through cutting, the moving direction is turned to 90 degrees again and is parallel to the initial edge, the cutting template is continuously moved, and one image is obtained through cutting every time the cutting template moves until the midpoint of the cutting template moves to the opposite edge.
Step eight: repeating the steps five to seven until the midpoint of the cutting template moves to the diagonal point of the starting point in the original image.
Preferably, when the size of the cutting template is consistent with that of the original image, the relationship between the moving times and the number of acquired samples is as follows:
L×a=h;
L×b=w;
a×b=n;
wherein L is the moving step length, a is the number of times of moving the cutting template in the vertical direction, b is the number of times of moving the cutting template in each horizontal direction, w and h are the width and length of the original image, and n is the number of new images which can be obtained by expanding one original image.
Compared with the prior art, the method for acquiring the mass samples based on the rock mass digital image has the advantages that:
(1) The invention can complete the whole flow work by computer programming, and provides a sufficient number of digital image samples for the machine learning of the rock-soil mass material and other related researches.
(2) The parameters of the image sample obtained by the invention can be manually adjusted, and the internal image information is coherent.
Drawings
For a clearer description of embodiments of the invention or of the prior art, the drawings which are used in the description of the embodiments or of the prior art will be briefly described, it being evident that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for obtaining a large number of samples based on digital images of rock mass according to the present disclosure.
Detailed Description
The following is a brief description of embodiments of the present invention with reference to the accompanying drawings. It is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and that all other embodiments obtained by a person having ordinary skill in the art without making creative efforts based on the embodiments in the present invention are within the protection scope of the present invention.
Fig. 1 shows a preferred embodiment of the invention, which is described in detail.
A method for obtaining a large number of samples based on digital images of rock mass as shown in fig. 1, comprising the steps of:
step one: the microscopic digital image of bentonite required for the study was obtained in a size of 1000 x 880.
Step two: based on the existing image, point symmetry and axisymmetry transformation are respectively carried out on four vertexes and four sides of the existing image, and a new image which is 3 times longer and wider than the original image and is consistent in image information is obtained, wherein the size of the new image is 3000 x 2640.
Step three: and combining the original image size to establish a cutting template, wherein the cutting template size is 1000 x 880. The midpoint of the cropping template is moved to one of the vertices of the original image in the new image, e.g., the top left corner vertex, i.e., the top 880 pixels and the top 1000 pixels from the new image, and the acquired image is cropped.
Step four: and selecting a cutting movement step length of 40 pixels, moving the cutting template rightwards along the edge of the original image on the new image, and cutting to obtain an image every time the cutting template moves until the middle point of the cutting template moves to the top right corner of the original image.
Step five: the moving direction is turned to 90 degrees, the cutting template is moved downwards by one step length along the right edge line of the original image on the new image, and an image is obtained through cutting.
Step six: the moving direction is turned to 90 degrees again, the cutting template is moved leftwards on the new image along the direction parallel to the upper edge line in the original image, and one image is obtained after cutting every time the cutting template is moved until the midpoint of the cutting template is moved to the left edge line of the original image.
Step seven: the moving direction is turned to 90 degrees again, the cutting template moves downwards by one step length along the left edge line of the original image on the new image, after cutting to obtain an image, the cutting template is turned to 90 degrees again to be parallel to the upper edge line, the cutting template continues to move rightwards, and each time the cutting template moves, the cutting to obtain an image is carried out until the midpoint of the cutting template moves to the right edge line.
Step eight: repeating the steps five to seven until the midpoint of the cutting template moves to the position of the right lower corner vertex of the original image. During this time, it is moved 22 times in the vertical direction, 25 times in each horizontal direction, i.e. 880 pixel distance in the vertical direction and 1000 pixel distance in each horizontal direction, a total of 550 image samples can be obtained to expand the digital image sample resources required for the study target material.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (1)
1. The method for acquiring the mass samples based on the rock mass digital image is characterized by comprising the following steps of:
step one: acquiring a rectangular digital image of a target material to be amplified;
step two: on the basis of the existing image, carrying out point symmetry and axisymmetry transformation on four vertexes and four sides of the existing image respectively to obtain a new image with the length and width 3 times that of the original image and consistent image information;
step three: establishing a cutting template, moving the middle point of the cutting template to one of the top points of the original image in the new image, and cutting to obtain the image;
step four: selecting a pixel distance with a certain size as a step length according to the size of an original image, moving a cutting template on a new image along one side of the original image, and cutting to obtain an image every time the cutting template moves until the middle point of the cutting template moves to the other vertex of the side;
step five: turning the moving direction by 90 degrees, moving a step length on the new image along the edge perpendicular to the initial edge in the original image, and cutting to obtain an image;
step six: turning the moving direction by 90 degrees again, moving the cutting template on the new image along the opposite direction of the initial edge in the original image, and cutting to obtain one image every time the cutting template is moved until the midpoint of the cutting template moves to the opposite edge perpendicular to the initial edge;
step seven: the moving direction is turned to 90 degrees again, the moving direction is consistent with the direction in the step five, one step length is moved, after an image is obtained through cutting, the moving direction is turned to 90 degrees again and is parallel to the initial edge, the cutting template is continuously moved, and one image is obtained through cutting every time the cutting template is moved until the midpoint of the cutting template is moved to the opposite edge;
step eight: repeating the steps five to seven until the midpoint of the cutting template moves to the diagonal point of the starting point in the original image;
when the size of the cutting template is consistent with that of the original image, the relation between the moving times and the number of acquired samples is as follows:
L×a=h;
L×b=w;
a×b=n;
wherein L is the moving step length, a is the number of times of moving the cutting template in the vertical direction, b is the number of times of moving the cutting template in each horizontal direction, w and h are the width and length of the original image, and n is the number of new images which can be obtained by expanding one original image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110260737.7A CN112802035B (en) | 2021-03-10 | 2021-03-10 | Method for obtaining large-batch samples based on rock mass digital images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110260737.7A CN112802035B (en) | 2021-03-10 | 2021-03-10 | Method for obtaining large-batch samples based on rock mass digital images |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112802035A CN112802035A (en) | 2021-05-14 |
CN112802035B true CN112802035B (en) | 2024-03-15 |
Family
ID=75816834
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110260737.7A Active CN112802035B (en) | 2021-03-10 | 2021-03-10 | Method for obtaining large-batch samples based on rock mass digital images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112802035B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010074265A1 (en) * | 2008-12-25 | 2010-07-01 | ユニバーサル・バイオ・リサーチ株式会社 | Method for pretreating specimen and method for assaying biological substance |
CN105809667A (en) * | 2015-01-21 | 2016-07-27 | 瞿志行 | Shading effect optimization method based on depth camera in augmented reality |
CN112150430A (en) * | 2020-09-21 | 2020-12-29 | 中国矿业大学(北京) | Numerical analysis method utilizing rock microscopic structure digital image |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9165388B2 (en) * | 2008-09-22 | 2015-10-20 | International Business Machines Corporation | Method of automatic cropping |
-
2021
- 2021-03-10 CN CN202110260737.7A patent/CN112802035B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010074265A1 (en) * | 2008-12-25 | 2010-07-01 | ユニバーサル・バイオ・リサーチ株式会社 | Method for pretreating specimen and method for assaying biological substance |
CN105809667A (en) * | 2015-01-21 | 2016-07-27 | 瞿志行 | Shading effect optimization method based on depth camera in augmented reality |
CN112150430A (en) * | 2020-09-21 | 2020-12-29 | 中国矿业大学(北京) | Numerical analysis method utilizing rock microscopic structure digital image |
Non-Patent Citations (2)
Title |
---|
Pore structure characterization and permeability prediction of coal samples based on SEM images;Shuai-Bing Song等;《Journal of Natural Gas Science and Engineering》;20190511;第160-171页 * |
基于数字图像的岩土体材料孔-裂隙结构表征及渗流特性研究;曹栩楼;《中国优秀硕士学位论文全文数据库 工程科技I辑》;20210115(第01期);B019-95 * |
Also Published As
Publication number | Publication date |
---|---|
CN112802035A (en) | 2021-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102017009276A1 (en) | TO PRODUCE A THREE-DIMENSIONAL MODEL FROM A SCANNED OBJECT | |
CN108280290B (en) | Concrete aggregate numerical model reconstruction method | |
Wu | Adaptive split-and-merge segmentation based on piecewise least-square approximation | |
CN112307553B (en) | Method for extracting and simplifying three-dimensional road model | |
CN107610230B (en) | 3D printing digital model sectioning and interface design method and application | |
Bamford et al. | A water immersion algorithm for cytological image segmentation | |
KR101425576B1 (en) | Method for acquiring and processing a three-dimensional data to product a precise wide-area scale model | |
CN110223376B (en) | Three-dimensional particle reconstruction method based on single accumulated particle material image | |
CN110675508A (en) | BIM model geometric figure simplification method | |
CN110608933B (en) | Permeable rock mass preparation method based on 3D printing | |
CN106463003A (en) | Fabricating three-dimensional objects with embossing | |
CN112802035B (en) | Method for obtaining large-batch samples based on rock mass digital images | |
CN108480859B (en) | Cutting method of wide multifunctional laser machine | |
CN116222381A (en) | Electrode coating size measurement method and device | |
CN112581621B (en) | Online extraction method for spatial dimension of three-dimensional point cloud steel plate | |
CN109359381B (en) | Laser path planning method based on voxels | |
CN113536617B (en) | Method for rapidly generating fine finite element model with complex structure | |
JP3394869B2 (en) | Manufacturing method of building materials | |
CN114220122A (en) | Palm vein sample category enhancement method and processing terminal | |
Norin et al. | Application of three-dimensional technologies in restoration of architectural decor elements | |
CN108823942B (en) | Cutting bed self-adaptive waste material cutting method | |
Santa et al. | Blueprints obtention by means of using digital image processing algorithms | |
DE102020215766A1 (en) | Additive manufacturing based on arrays of offset-related, signed distances | |
AU8797698A (en) | Method of constructing a substantial image using honeycomb structure elements | |
CN113591321B (en) | Method for generating three-dimensional high-simulation structural model of mine earth-rock mixture |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |